Browse All Artificial Intelligence Content (1132)

Paula Santamaría and Julia Schröder Langhaeuser present a production Retrieval-Augmented Generation (RAG) architecture built on Azure Database for PostgreSQL, explaining why Postgres can be a solid foundation for RAG at scale and what it takes to move from prototype to production with performance tuning and monitoring.

Natalie Guevara explains how GitHub Copilot is improving token efficiency in longer sessions by caching repeated prompt context, loading tool definitions on demand, and routing requests to the best-fit model via Auto model selection. The post also shares practical habits for reducing credit burn in day-to-day Copilot workflows.

Amar Digamber Patil explains what viewers will learn from the Budget Bytes series, focusing on building AI-powered applications on Azure SQL and how to evolve from simple setups to more scalable architectures while keeping costs within a $25 budget.

Amar Digamber Patil introduces the Budget Bytes series and explains what viewers will learn about building AI-powered apps with Azure SQL, covering approaches that start simple and scale up while staying within a $25 budget.

Rob Lefferts summarizes Microsoft’s positioning as a Leader in Forrester’s 2026 XDR Wave and explains the security platform themes Microsoft is emphasizing: cross-domain signal correlation, attack disruption, built-in threat intelligence, and SOC workflows powered by Microsoft Defender, Microsoft Sentinel, and Security Copilot.

GitHub announces the general availability of the GitHub Copilot app, a native desktop experience focused on agent-driven development. GitHub highlights starting sessions from issues and pull requests, running work in parallel, and using a unified workspace with full GitHub context to take tasks from issue to merge.

Allison announces a new GitHub Copilot enterprise governance control that lets admins disable bypassing permission prompts (“yolo mode” / auto-approve) in Copilot clients. The update explains where to place the enterprise-managed settings file, how it’s applied to licensed users, and which VS Code versions respect the policy.

Sandeep Deo explains how AI is speeding up identity-based attacks and what Microsoft is changing across Entra and Defender to help teams prevent, detect, and respond faster. The post highlights unified identity risk scoring, improved Entra ID Protection views, least-privilege response roles, and agent-driven recommendations for Conditional Access.

Jan Krivanek introduces the Microsoft Binlog MCP Server, an MCP server that lets AI assistants (including GitHub Copilot) query MSBuild .binlog files using 15 purpose-built tools for failure diagnosis, property tracing, performance bottleneck analysis, and build-to-build comparisons across Visual Studio, VS Code, and CLI workflows.

amitch announces a preview ServiceNow connector that can query Microsoft OneLake data in place (zero-copy), aiming to reduce ETL and keep a single governed data foundation across Microsoft Fabric analytics and downstream operational workflows.

yairgil explains how the Azure Copilot Observability Agent in Azure Monitor helps teams investigate AKS incidents by correlating metrics, logs, traces, Kubernetes events, and change history into an evidence-backed root-cause narrative with recommended next steps.

Allison announces general availability of auto model selection in GitHub Copilot Chat on github.com and the GitHub mobile app, explaining how auto routes requests to different AI models based on task complexity and real-time availability, and how it affects transparency, policy controls, and token billing.

Allison announces GitHub Copilot’s new agent finder, which discovers and ranks agent capabilities from a registry you choose, with enterprise controls over what resources can be surfaced and used.

GitHub shares how ASOS adopted GitHub Copilot after migrating to GitHub, focusing on reducing developer toil and speeding up delivery. It highlights using Copilot to streamline pull requests and building custom AI agents so engineers can spend less time on routine work and more time shipping features.

jiang_jenny1 introduces the Fabric Spark Operations Skill (preview), an AI-assisted, read-only troubleshooting tool for Spark workloads in Microsoft Fabric. It turns common investigations—failed notebooks, pipeline failures, session triage, and performance issues—into natural-language commands that produce a severity-ranked diagnostic report with fix recommendations and links back to Fabric.

Waldek Mastykarz explains why AI coding agent extensions that perform well alone can degrade results when installed alongside other extensions, and how to measure and reduce these composition effects in real developer workspaces.

Visual Studio Code shares a quick set of “top tips” from the engineering team, highlighting practical editor features like subagents, favorite shortcuts, and a few hidden easter eggs, plus a mention of event agent markdown files and GitHub Copilot-related workflows.

Allison announces that GitHub Copilot individual plan sign-ups are reopening (Student, Pro, Pro+, and Max) and outlines immediate changes to how upgrades and continued usage work when you approach included usage and spending limits.

Allison announces the general availability of the GitHub Copilot app for macOS, Windows, and Linux, positioning it as a desktop workflow for agent-driven development. The post highlights starting sessions from issues or pull requests, running parallel sessions per repo, reviewing diffs, and using canvases, cloud automations, and MCP-connected tools.

Ryan Caldwell and Bhavya U explain how the VS Code team is reducing GitHub Copilot’s token usage (and improving latency) in agentic sessions, with concrete changes to prompt caching, tool-definition loading, and transport choices across OpenAI and Anthropic models.

Natalie Guevara explains Git worktrees as a practical way to work on multiple branches at once without stashing or constantly switching contexts, and shows the core commands plus the trade-offs to watch for. The article also connects worktrees to parallel workflows used by tools like the GitHub Copilot app.

Affan Dar and Charles Feddersen share how Microsoft is investing in PostgreSQL upstream and how that work feeds into Azure Database for PostgreSQL, including scaling features, HorizonDB, developer tooling, and a look at building AI pipelines inside Postgres.

Pamela Fox presents a practical design discussion on building Model Context Protocol (MCP) servers for PostgreSQL, focusing on how tool interfaces affect LLM query accuracy and safety. She compares free-form SQL vs typed tools, and walks through common failure modes like SQL injection, risky mutations, and expensive queries.

Matt McFarland explains how PostgreSQL developer tooling is being extended from the VS Code PostgreSQL extension into AI-driven environments like Cursor and the GitHub Copilot CLI, using an MCP server as a shared interface for connections, queries, schema inspection, and performance analysis.

Allison announces that GitHub Models is being retired and is no longer available to new organizations and enterprises, while existing customers can continue using the playground, API, and models for now.

dotnet presents a short walkthrough on modernizing existing .NET applications and quickly adding agentic (AI agent) capabilities, focusing on practical steps and resources for .NET developers.

dotnet presents a session on using GitHub Copilot to modernize legacy .NET Framework applications, focusing on AI-assisted workflows to assess, plan, and execute upgrades to the latest .NET with less manual effort and lower migration risk.

James Montemagno, Burke Holland, and Pierce Boggan demo “vibe coding” workflows in VS Code using Claude Fable 5 with GitHub Copilot, focusing on what the model enables for day-to-day AI-assisted coding and how it fits into real development habits.

Reynald Adolphe, Kyle Cutler, Giuseppe Ciance, and Vritant Bhardwaj recap the major Visual Studio Code and GitHub Copilot updates from the past month, with demos of features like the Integrated Browser, Issue Reporting improvements, and BYOK enhancements.

Microsoft Developer shares a short clip from Cozy AI Kitchen featuring John Maeda and Griffin Norris, touching on robots, AI agents, and Copilot in the context of Microsoft’s AI ecosystem.

Visual Studio Code introduces “bring your own key” support, letting developers use their own model provider API keys with VS Code and GitHub Copilot without signing in, and points to the setup guide for enabling expanded model choice.

Griffin Norris demonstrates how AI agents and Microsoft Copilot can speed up robotics development by generating robot control code from natural language, connecting robots to AI models via MCP servers, and adding vision-based scene understanding for interactive, feedback-driven control.

Allison announces that GitHub Code Quality moves from public preview to general availability on July 20, 2026, including new org-level rollout and reporting features plus a new pricing model that combines per-committer licensing with metered AI usage and GitHub Actions minutes for CodeQL scans.

Satya Nadella highlights an Azure milestone: a new performance record for a leading LLM training benchmark at extreme scale, achieved through full-stack work across silicon, systems, networking, and software in partnership with NVIDIA.

Daniel Costea shows how to use ChatClient and Microsoft Agent Framework middleware to turn a basic .NET AI agent into something you can run in production, with guardrails for safety, privacy, observability, and cost control, using an ASP.NET Core-style middleware mental model.

azinh17 breaks down how Azure achieved a top MLPerf Training v6.0 result for Llama 3.1 405B, training at extreme scale across 8,192 GPUs. The post focuses on the cluster and network architecture choices—NVLink scale-up domains, Azure’s MRC fabric, and topology-aware parallelism mapping—that kept step time stable as the system scaled.

GitHub shows how the GitHub Copilot app helps move work from an issue to a merged pull request, using features like plan mode and agent merge to guide agentic changes, handle CI failures, and land PRs with more control.

Waldek Mastykarz explains why AI coding agents often keep using deprecated tooling (like legacy CLIs) even after teams ship replacements, and outlines practical ways to measure and correct agent behavior using extensions, explicit deprecation signals, and better naming.

Chris Welsch reports on İmeceMobil, an agriculture platform built on Microsoft Azure that helps Turkish farmers use AI-driven satellite imagery analysis, hyperlocal weather alerts, and expert guidance to improve crop decisions. The piece also highlights the Azure services and security tooling used to run the app at scale.

Visual Studio Code shows how to use VS Code’s language model system to bring your own AI provider without signing into Copilot, including native providers like Anthropic, custom endpoints, third-party integrations, and running local models offline.